shopify-known-pitfalls
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a user's codebase to identify anti-patterns, which introduces a surface for indirect prompt injection if the scanned files contain malicious instructions.
- Ingestion points: The skill uses
GrepandReadtools to scan project directories as described inSKILL.mdandreferences/pitfall-scan-script.md. - Boundary markers: No specific delimiters are used to wrap the code being analyzed to prevent the agent from interpreting instructions within it.
- Capability inventory: The skill leverages file system tools (
Read,Grep) to inspect the environment. - Sanitization: There is no evidence of filtering or sanitization of the content read from the codebase.
Audit Metadata